Muse Spark Open

• Type: Generation
• Capabilities: reasoning
• Cache read: $0.15 per 1M input tokens (0.12× standard input price). See prompt caching.

Overview

Muse Spark Open is Meta's first open-weight model from its flagship Muse Spark line. It has 816 billion total parameters with 42 billion active per token and a one-million-token context window. Meta built it for coding, multi-step reasoning, and agentic workflows that call tools, recover from errors, and sustain long-running tasks. At release it was the highest-scoring open-weight model from a U.S. lab on the Artificial Analysis Intelligence Index.

---

Reasoning: This model reasons before it responds. Set the depth per request with reasoning_effort: low, medium, high or xhigh (the default). Use high or xhigh for complex coding and agentic tasks, and low for latency-sensitive work. Reasoning can't be fully disabled: none and minimal use the lowest setting (low), and max uses xhigh.

Input: Text only on Doubleword.

Reasoning efforts

• Supported: none, minimal, low, medium, high, xhigh, max

See the reasoning effort guide for request examples.

Pricing

Priority	Input Tokens (per 1M)	Cache Read Tokens (per 1M)	Output Tokens (per 1M)
Realtime1	$1.25	$0.15	$4.25
Async	$1.25	$0.15	$4.25
Batch (24h)	$1.25	$0.15	$4.25

Playground

Open this model in the Playground.

Footnotes

1. Realtime availability is limited. Doubleword is primarily a batch API. ↩